Trjtdtk

Why do I get negative height?

Where would I need my direct neural interface to be implanted?

Explaination of a justification: additive functors preserve limits

Could the museum Saturn V's be refitted for one more flight?

Is it inappropriate for a student to attend their mentor's dissertation defense?

What do you call someone who asks many questions?

How do I exit BASH while loop using modulus operator?

Finitely generated matrix groups whose eigenvalues are all algebraic

Was the Stack Exchange "Happy April Fools" page fitting with the '90's code?

Using "tail" to follow a file without displaying the most recent lines

How to stretch the corners of this image so that it looks like a perfect rectangle?

Mathematica command that allows it to read my intentions

Array of objects return object when condition matched

How to compactly explain secondary and tertiary characters without resorting to stereotypes?

How seriously should I take size and weight limits of hand luggage?

meaning of 腰を落としている

What Exploit Are These User Agents Trying to Use?

Does Fukaya see all symplectic topology?

Does the Cone of Cold spell freeze water?

Theorists sure want true answers to this!

What is the opposite of "eschatology"?

Why would the Red Woman birth a shadow if she worshipped the Lord of the Light?

Why is the sentence "Das ist eine Nase" correct?

How badly should I try to prevent a user from XSSing themselves?

Using K-prototypes algorithm to cluster gdelt data by country

0

1

$begingroup$

I want to cluster GDLET data by country using the k-prototypes algorithm. GDELT returns a list of themes as seen in this SE post.

I was looking at the example data frame in this blog post as a reference. My idea is to sum theme occurrence by country and use the top themes as inputs, then my data frame would look like

 t1 t2 t3 t4 t5 t1 t2 t3 t4 t5 ...
country_1 0 0 0 1 0 1 0 0 0 0 ...
 .
 .
 .
 |_____________| |____________|
 #1 theme #2 theme

I would then be able to cluster the countries using this data frame. The above mentioned SE post says that clustering will not work well for that question, but I feel like what I am trying to do is different, but I have not used k-modes/k-prototypes and was hoping someone who had could let me know if this is a valid approach. There will be other data associated besides themes, but this is the basic approach I am planning for the majority of the data frame.

Thanks

clustering

share|improve this question

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

$endgroup$

add a comment | 

0

1

$begingroup$

I want to cluster GDLET data by country using the k-prototypes algorithm. GDELT returns a list of themes as seen in this SE post.

I was looking at the example data frame in this blog post as a reference. My idea is to sum theme occurrence by country and use the top themes as inputs, then my data frame would look like

 t1 t2 t3 t4 t5 t1 t2 t3 t4 t5 ...
country_1 0 0 0 1 0 1 0 0 0 0 ...
 .
 .
 .
 |_____________| |____________|
 #1 theme #2 theme

I would then be able to cluster the countries using this data frame. The above mentioned SE post says that clustering will not work well for that question, but I feel like what I am trying to do is different, but I have not used k-modes/k-prototypes and was hoping someone who had could let me know if this is a valid approach. There will be other data associated besides themes, but this is the basic approach I am planning for the majority of the data frame.

Thanks

clustering

share|improve this question

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

$endgroup$

add a comment | 

$begingroup$

I want to cluster GDLET data by country using the k-prototypes algorithm. GDELT returns a list of themes as seen in this SE post.

I was looking at the example data frame in this blog post as a reference. My idea is to sum theme occurrence by country and use the top themes as inputs, then my data frame would look like

 t1 t2 t3 t4 t5 t1 t2 t3 t4 t5 ...
country_1 0 0 0 1 0 1 0 0 0 0 ...
 .
 .
 .
 |_____________| |____________|
 #1 theme #2 theme

I would then be able to cluster the countries using this data frame. The above mentioned SE post says that clustering will not work well for that question, but I feel like what I am trying to do is different, but I have not used k-modes/k-prototypes and was hoping someone who had could let me know if this is a valid approach. There will be other data associated besides themes, but this is the basic approach I am planning for the majority of the data frame.

Thanks

clustering

share|improve this question

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

$endgroup$

 t1 t2 t3 t4 t5 t1 t2 t3 t4 t5 ...
country_1 0 0 0 1 0 1 0 0 0 0 ...
 .
 .
 .
 |_____________| |____________|
 #1 theme #2 theme

share|improve this question

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

share|improve this question

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011

asked Mar 27 at 2:09

Jeff TiltonJeff Tilton

1011